{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:HGCCVCZPEPAT7AWAXE4V32NIOY","short_pith_number":"pith:HGCCVCZP","schema_version":"1.0","canonical_sha256":"39842a8b2f23c13f82c0b9395de9a876082797494627a4a776a9d56b5559efa5","source":{"kind":"arxiv","id":"2009.07118","version":2},"attestation_state":"computed","paper":{"title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Timo Schick","submitted_at":"2020-09-15T14:18:53Z","abstract_excerpt":"When scaled to hundreds of billions of parameters, pretrained language models such as GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance. However, enormous amounts of compute are required for training and applying such big models, resulting in a large carbon footprint and making it difficult for researchers and practitioners to use them. We show that performance similar to GPT-3 can be obtained with language models that are much \"greener\" in that their parameter count is several orders of magnitude smaller. This is achieved by converting textual inputs into cloze questions that"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2009.07118","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-09-15T14:18:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"5d05251119ebadb70386e6bdf2c02c32a7232cd95062c14abfed4e0e02ce80e2","abstract_canon_sha256":"7e0e26936f983184de49ed9ac6ba7e687f23153eb0f27c03e533e07f1198ad0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:30:59.582938Z","signature_b64":"hDsnjlot1qB/rbAOG0dd1objlN7Dqmp/MlfsZhA416BB9pf8wbPQIyUhJy1KVayb+pwUMt9NT2pbVk/XOK+XDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39842a8b2f23c13f82c0b9395de9a876082797494627a4a776a9d56b5559efa5","last_reissued_at":"2026-07-05T02:30:59.582444Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:30:59.582444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Timo Schick","submitted_at":"2020-09-15T14:18:53Z","abstract_excerpt":"When scaled to hundreds of billions of parameters, pretrained language models such as GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance. However, enormous amounts of compute are required for training and applying such big models, resulting in a large carbon footprint and making it difficult for researchers and practitioners to use them. We show that performance similar to GPT-3 can be obtained with language models that are much \"greener\" in that their parameter count is several orders of magnitude smaller. This is achieved by converting textual inputs into cloze questions that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.07118","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.07118/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2009.07118","created_at":"2026-07-05T02:30:59.582503+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.07118v2","created_at":"2026-07-05T02:30:59.582503+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.07118","created_at":"2026-07-05T02:30:59.582503+00:00"},{"alias_kind":"pith_short_12","alias_value":"HGCCVCZPEPAT","created_at":"2026-07-05T02:30:59.582503+00:00"},{"alias_kind":"pith_short_16","alias_value":"HGCCVCZPEPAT7AWA","created_at":"2026-07-05T02:30:59.582503+00:00"},{"alias_kind":"pith_short_8","alias_value":"HGCCVCZP","created_at":"2026-07-05T02:30:59.582503+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19957","citing_title":"Modest, artistic, and radical solutions to the environmental impact of image-generating machine learning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15015","citing_title":"Small, Private Language Models as Teammates for Educational Assessment Design","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2502.16759","citing_title":"Can Explanations Improve Recommendations? Evidence from Prediction-Informed Explanations","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2104.08773","citing_title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2208.03299","citing_title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","ref_index":242,"is_internal_anchor":false},{"citing_arxiv_id":"2406.06608","citing_title":"The Prompt Report: A Systematic Survey of Prompt Engineering Techniques","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05732","citing_title":"Graph Topology Information Enhanced Heterogeneous Graph Representation Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2205.01068","citing_title":"OPT: Open Pre-trained Transformer Language Models","ref_index":192,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HGCCVCZPEPAT7AWAXE4V32NIOY","json":"https://pith.science/pith/HGCCVCZPEPAT7AWAXE4V32NIOY.json","graph_json":"https://pith.science/api/pith-number/HGCCVCZPEPAT7AWAXE4V32NIOY/graph.json","events_json":"https://pith.science/api/pith-number/HGCCVCZPEPAT7AWAXE4V32NIOY/events.json","paper":"https://pith.science/paper/HGCCVCZP"},"agent_actions":{"view_html":"https://pith.science/pith/HGCCVCZPEPAT7AWAXE4V32NIOY","download_json":"https://pith.science/pith/HGCCVCZPEPAT7AWAXE4V32NIOY.json","view_paper":"https://pith.science/paper/HGCCVCZP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.07118&json=true","fetch_graph":"https://pith.science/api/pith-number/HGCCVCZPEPAT7AWAXE4V32NIOY/graph.json","fetch_events":"https://pith.science/api/pith-number/HGCCVCZPEPAT7AWAXE4V32NIOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HGCCVCZPEPAT7AWAXE4V32NIOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HGCCVCZPEPAT7AWAXE4V32NIOY/action/storage_attestation","attest_author":"https://pith.science/pith/HGCCVCZPEPAT7AWAXE4V32NIOY/action/author_attestation","sign_citation":"https://pith.science/pith/HGCCVCZPEPAT7AWAXE4V32NIOY/action/citation_signature","submit_replication":"https://pith.science/pith/HGCCVCZPEPAT7AWAXE4V32NIOY/action/replication_record"}},"created_at":"2026-07-05T02:30:59.582503+00:00","updated_at":"2026-07-05T02:30:59.582503+00:00"}